Lab 11

Author

Christine Raj

Libraries

library(ggplot2)
library(plotly)

Attaching package: 'plotly'
The following object is masked from 'package:ggplot2':

    last_plot
The following object is masked from 'package:stats':

    filter
The following object is masked from 'package:graphics':

    layout
library(tidyverse)
── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.2     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ lubridate 1.9.2     ✔ tibble    3.2.1
✔ purrr     1.0.2     ✔ tidyr     1.3.0
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks plotly::filter(), stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(dplyr)
library(tidyr)
library(zoo)

Attaching package: 'zoo'

The following objects are masked from 'package:base':

    as.Date, as.Date.numeric

Importing Data

## data extracted from New York Times state-level data from NYT Github repository
# https://github.com/nytimes/covid-19-data

## state-level population information from us_census_data available on GitHub repository:
# https://github.com/COVID19Tracking/associated-data/tree/master/us_census_data

### FINISH THE CODE HERE ###
# load COVID state-level data from NYT
if (!file.exists("us_census_2018_population_estimates_states.csv"))
  download.file(
    url = "https://raw.githubusercontent.com/COVID19Tracking/associated-data/master/us_census_data/us_census_2018_population_estimates_states.csv",
    destfile = "us_census_2018_population_estimates_states.csv",
    method = "libcurl",
    timeout = 60
    )
state_pops <- data.table::fread("us_census_2018_population_estimates_states.csv")
if (!file.exists("us_states.csv"))
  download.file(
    url = "https://raw.githubusercontent.com/nytimes/covid-19-data/master/us-states.csv",
    destfile = "us_states.csv",
    method = "libcurl",
    timeout = 60
    )
cv_states <- data.table::fread("us_states.csv")
state_pops$abb <- state_pops$state
state_pops$state <- state_pops$state_name
state_pops$state_name <- NULL

cv_states <- merge(cv_states, state_pops, by="state")

Checking Data

dim(cv_states)
[1] 58094     9
head(cv_states)
     state       date fips cases deaths geo_id population pop_density abb
1: Alabama 2020-03-13    1     6      0      1    4887871    96.50939  AL
2: Alabama 2020-03-14    1    12      0      1    4887871    96.50939  AL
3: Alabama 2020-03-15    1    23      0      1    4887871    96.50939  AL
4: Alabama 2020-03-16    1    29      0      1    4887871    96.50939  AL
5: Alabama 2020-03-17    1    39      0      1    4887871    96.50939  AL
6: Alabama 2020-03-18    1    51      0      1    4887871    96.50939  AL
tail(cv_states)
     state       date fips  cases deaths geo_id population pop_density abb
1: Wyoming 2023-03-18   56 185640   2009     56     577737    5.950611  WY
2: Wyoming 2023-03-19   56 185640   2009     56     577737    5.950611  WY
3: Wyoming 2023-03-20   56 185640   2009     56     577737    5.950611  WY
4: Wyoming 2023-03-21   56 185800   2014     56     577737    5.950611  WY
5: Wyoming 2023-03-22   56 185800   2014     56     577737    5.950611  WY
6: Wyoming 2023-03-23   56 185800   2014     56     577737    5.950611  WY
str(cv_states)
Classes 'data.table' and 'data.frame':  58094 obs. of  9 variables:
 $ state      : chr  "Alabama" "Alabama" "Alabama" "Alabama" ...
 $ date       : IDate, format: "2020-03-13" "2020-03-14" ...
 $ fips       : int  1 1 1 1 1 1 1 1 1 1 ...
 $ cases      : int  6 12 23 29 39 51 78 106 131 157 ...
 $ deaths     : int  0 0 0 0 0 0 0 0 0 0 ...
 $ geo_id     : int  1 1 1 1 1 1 1 1 1 1 ...
 $ population : int  4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 ...
 $ pop_density: num  96.5 96.5 96.5 96.5 96.5 ...
 $ abb        : chr  "AL" "AL" "AL" "AL" ...
 - attr(*, ".internal.selfref")=<externalptr> 
 - attr(*, "sorted")= chr "state"

We need to change the variable type of states and abb. We also need to make the date an actual date we can pull from rather than just an IDate.

# format the date
cv_states$date <- as.Date(cv_states$date, format="%Y-%m-%d")

# format the state and state abbreviation (abb) variables
state_list <- unique(cv_states$state)
cv_states$state <- factor(cv_states$state, levels = state_list)
abb_list <- unique(cv_states$abb)
cv_states$abb <- factor(cv_states$abb, levels = abb_list)

### FINISH THE CODE HERE 
# order the data first by state, second by date
cv_states = cv_states[order(cv_states$state, cv_states$date),]

# Confirm the variables are now correctly formatted
str(cv_states)
Classes 'data.table' and 'data.frame':  58094 obs. of  9 variables:
 $ state      : Factor w/ 52 levels "Alabama","Alaska",..: 1 1 1 1 1 1 1 1 1 1 ...
 $ date       : Date, format: "2020-03-13" "2020-03-14" ...
 $ fips       : int  1 1 1 1 1 1 1 1 1 1 ...
 $ cases      : int  6 12 23 29 39 51 78 106 131 157 ...
 $ deaths     : int  0 0 0 0 0 0 0 0 0 0 ...
 $ geo_id     : int  1 1 1 1 1 1 1 1 1 1 ...
 $ population : int  4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 4887871 ...
 $ pop_density: num  96.5 96.5 96.5 96.5 96.5 ...
 $ abb        : Factor w/ 52 levels "AL","AK","AZ",..: 1 1 1 1 1 1 1 1 1 1 ...
 - attr(*, ".internal.selfref")=<externalptr> 
head(cv_states)
     state       date fips cases deaths geo_id population pop_density abb
1: Alabama 2020-03-13    1     6      0      1    4887871    96.50939  AL
2: Alabama 2020-03-14    1    12      0      1    4887871    96.50939  AL
3: Alabama 2020-03-15    1    23      0      1    4887871    96.50939  AL
4: Alabama 2020-03-16    1    29      0      1    4887871    96.50939  AL
5: Alabama 2020-03-17    1    39      0      1    4887871    96.50939  AL
6: Alabama 2020-03-18    1    51      0      1    4887871    96.50939  AL
tail(cv_states)
     state       date fips  cases deaths geo_id population pop_density abb
1: Wyoming 2023-03-18   56 185640   2009     56     577737    5.950611  WY
2: Wyoming 2023-03-19   56 185640   2009     56     577737    5.950611  WY
3: Wyoming 2023-03-20   56 185640   2009     56     577737    5.950611  WY
4: Wyoming 2023-03-21   56 185800   2014     56     577737    5.950611  WY
5: Wyoming 2023-03-22   56 185800   2014     56     577737    5.950611  WY
6: Wyoming 2023-03-23   56 185800   2014     56     577737    5.950611  WY
# Inspect the range values for each variable. What is the date range? The range of cases and deaths?
head(cv_states)
     state       date fips cases deaths geo_id population pop_density abb
1: Alabama 2020-03-13    1     6      0      1    4887871    96.50939  AL
2: Alabama 2020-03-14    1    12      0      1    4887871    96.50939  AL
3: Alabama 2020-03-15    1    23      0      1    4887871    96.50939  AL
4: Alabama 2020-03-16    1    29      0      1    4887871    96.50939  AL
5: Alabama 2020-03-17    1    39      0      1    4887871    96.50939  AL
6: Alabama 2020-03-18    1    51      0      1    4887871    96.50939  AL
summary(cv_states)
           state            date                 fips           cases         
 Washington   : 1158   Min.   :2020-01-21   Min.   : 1.00   Min.   :       1  
 Illinois     : 1155   1st Qu.:2020-12-06   1st Qu.:16.00   1st Qu.:  112125  
 California   : 1154   Median :2021-09-11   Median :29.00   Median :  418120  
 Arizona      : 1153   Mean   :2021-09-10   Mean   :29.78   Mean   :  947941  
 Massachusetts: 1147   3rd Qu.:2022-06-17   3rd Qu.:44.00   3rd Qu.: 1134318  
 Wisconsin    : 1143   Max.   :2023-03-23   Max.   :72.00   Max.   :12169158  
 (Other)      :51184                                                          
     deaths           geo_id        population        pop_density       
 Min.   :     0   Min.   : 1.00   Min.   :  577737   Min.   :    1.292  
 1st Qu.:  1598   1st Qu.:16.00   1st Qu.: 1805832   1st Qu.:   43.659  
 Median :  5901   Median :29.00   Median : 4468402   Median :  107.860  
 Mean   : 12553   Mean   :29.78   Mean   : 6397965   Mean   :  423.031  
 3rd Qu.: 15952   3rd Qu.:44.00   3rd Qu.: 7535591   3rd Qu.:  229.511  
 Max.   :104277   Max.   :72.00   Max.   :39557045   Max.   :11490.120  
                                                     NA's   :1106       
      abb       
 WA     : 1158  
 IL     : 1155  
 CA     : 1154  
 AZ     : 1153  
 MA     : 1147  
 WI     : 1143  
 (Other):51184  
min(cv_states$date)
[1] "2020-01-21"
max(cv_states$date)
[1] "2023-03-23"

The date range is from Jan 21, 2020 to March 23, 2023. Cases range from 1 to 12169158 and deaths range from 0 - 104277.

Cases, Deaths, and Outliers

for (i in 1:length(state_list)) {
  cv_subset = subset(cv_states, state == state_list[i])
  cv_subset = cv_subset[order(cv_subset$date),]

  # add starting level for new cases and deaths
  cv_subset$new_cases = cv_subset$cases[1]
  cv_subset$new_deaths = cv_subset$deaths[1]

  ### FINISH THE CODE HERE
  for (j in 2:nrow(cv_subset)) {
    cv_subset$new_cases[j] = cv_subset$cases[j] - cv_subset$cases[j - 1]
    cv_subset$new_deaths[j] = cv_subset$deaths[j] - cv_subset$deaths[j - 1]
  }

  # include in main dataset
  cv_states$new_cases[cv_states$state==state_list[i]] = cv_subset$new_cases
  cv_states$new_deaths[cv_states$state==state_list[i]] = cv_subset$new_deaths
}
# Focus on recent dates
cv_states <- cv_states %>% dplyr::filter(date >= "2021-06-01")
### FINISH THE CODE HERE
# Inspect outliers in new_cases using plotly
p1<-ggplot(cv_states, aes(x = date, y = new_cases, color = state)) +  geom_point(size = .5, alpha = 0.5)
ggplotly(p1)
#p1<-NULL # to clear from workspace

California, Texas and Florida have high outliers. Florida, Colorado, Pennsylvania, Tennessee, Kentucky, Texas, Washington, Nebraska, and other states have outliers because they have data points for new cases that are below zero which is not possible.

p2<-ggplot(cv_states, aes(x = date, y = new_deaths, color = state)) + geom_point(size = .5, alpha = 0.5)
ggplotly(p2)
#p2<-NULL # to clear from workspace
# set negative new case or death counts to 0
cv_states$new_cases[cv_states$new_cases<0] = 0
cv_states$new_deaths[cv_states$new_deaths<0] = 0
# Recalculate `cases` and `deaths` as cumulative sum of updated `new_cases` and `new_deaths`
for (i in 1:length(state_list)) {
  cv_subset = subset(cv_states, state == state_list[i])

  # add starting level for new cases and deaths
  cv_subset$cases = cv_subset$cases[1]
  cv_subset$deaths = cv_subset$deaths[1]

  ### FINISH CODE HERE
  for (j in 2:nrow(cv_subset)) {
    cv_subset$cases[j] = cv_subset$new_cases[j] + cv_subset$cases[j - 1]
    cv_subset$deaths[j] = cv_subset$new_deaths[j] + cv_subset$cases[j - 1]
  }
  # include in main dataset
  cv_states$cases[cv_states$state==state_list[i]] = cv_subset$cases
  cv_states$deaths[cv_states$state==state_list[i]] = cv_subset$deaths
}

# Smooth new counts
cv_states$new_cases = zoo::rollmean(cv_states$new_cases, k=7, fill=NA, align='right') %>% round(digits = 0)
cv_states$new_deaths = zoo::rollmean(cv_states$new_deaths, k=7, fill=NA, align='right') %>% round(digits = 0)
# Inspect data again interactively
p2<-ggplot(cv_states, aes(x = date, y = new_deaths, color = state)) + geom_line() + geom_point(size = .5, alpha = 0.5)
ggplotly(p2)
#p2=NULL

table(is.na(cv_states))

 FALSE   TRUE 
377419    673 

Step 5

### FINISH CODE HERE
# add population normalized (by 100,000) counts for each variable
cv_states$per100k =  as.numeric(format(round(cv_states$cases/(cv_states$population/100000),1),nsmall=1))
cv_states$newper100k =  as.numeric(format(round(cv_states$new_cases/(cv_states$population/100000),1),nsmall=1))
Warning: NAs introduced by coercion
cv_states$deathsper100k =  as.numeric(format(round(cv_states$deaths/(cv_states$population/100000),1),nsmall=1))
cv_states$newdeathsper100k =  as.numeric(format(round(cv_states$new_deaths/(cv_states$population/100000),1),nsmall=1))
Warning: NAs introduced by coercion
# add a naive_CFR variable = deaths / cases
cv_states = cv_states %>% mutate(naive_CFR = round((deaths*100/cases),2))

# create a `cv_states_today` variable
cv_states_today = subset(cv_states, date==max(cv_states$date))

Scatterplots

# pop_density vs. cases
cv_states_today %>% 
  plot_ly(x = ~pop_density, y = ~cases, 
          type = 'scatter', mode = 'markers', color = ~state,
          size = ~population, sizes = c(5, 70), marker = list(sizemode='diameter', opacity=0.5))
Warning: Ignoring 1 observations
Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Pop Density vs Cases after Filtering

# filter out "District of Columbia"
cv_states_today_filter <- cv_states_today %>% filter(state!="District of Columbia")

# pop_density vs. cases after filtering
cv_states_today_filter %>% 
  plot_ly(x = ~pop_density, y = ~cases, 
          type = 'scatter', mode = 'markers', color = ~state,
          size = ~population, sizes = c(5, 70), marker = list(sizemode='diameter', opacity=0.5))
Warning: Ignoring 1 observations
Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Pop Density vs Deaths per 100k

# pop_density vs. deathsper100k
cv_states_today_filter %>% 
  plot_ly(x = ~pop_density, y = ~deathsper100k,
          type = 'scatter', mode = 'markers', color = ~state,
          size = ~population, sizes = c(5, 70), marker = list(sizemode='diameter', opacity=0.5))
Warning: Ignoring 1 observations
Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Adding Hoverinfo

# Adding hoverinfo
cv_states_today_filter %>% 
  plot_ly(x = ~pop_density, y = ~deathsper100k,
          type = 'scatter', mode = 'markers', color = ~state,
          size = ~population, sizes = c(5, 70), marker = list(sizemode='diameter', opacity=0.5),
          hoverinfo = 'text',
          text = ~paste( paste(state, ":", sep=""), paste(" Cases per 100k: ", per100k, sep="") , 
                         paste(" Deaths per 100k: ", deathsper100k, sep=""), sep = "<br>")) %>%
  layout(title = "Population-normalized COVID-19 deaths (per 100k) vs. population density for US states",
                  yaxis = list(title = "Deaths per 100k"), xaxis = list(title = "Population Density"),
         hovermode = "compare")
Warning: Ignoring 1 observations
Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Step 7: Explore trend interactively

### FINISH CODE HERE
p <- ggplot(cv_states_today, aes(x=pop_density, y=deathsper100k, size=population)) + geom_point() + geom_smooth() + labs(title = "Scatterplot of pop_density vs. newdeathsper100k",   x = "Population Density",
       y = "New Deaths per 100k")
ggplotly(p)
`geom_smooth()` using method = 'loess' and formula = 'y ~ x'
Warning: Removed 1 rows containing non-finite values (`stat_smooth()`).
Warning: The following aesthetics were dropped during statistical transformation: size
ℹ This can happen when ggplot fails to infer the correct grouping structure in
  the data.
ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
  variable into a factor?

I don’t think population density is a correlate of new deaths per 100k.

Step 8: Multiple Line Charts

### FINISH CODE HERE
# Line chart for naive_CFR for all states over time using `plot_ly()`
plot_ly(cv_states, x = ~date, y = ~naive_CFR, color = ~state, type = 'scatter', mode = 'lines')
Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

Warning in RColorBrewer::brewer.pal(N, "Set2"): n too large, allowed maximum for palette Set2 is 8
Returning the palette you asked for with that many colors

States that had an increase in September decreased over time and had other spikes in December.

### FINISH CODE HERE
# Line chart for Florida showing new_cases and new_deaths together
cv_states %>% filter(state=="Florida") %>% plot_ly(x = ~date, y = ~new_cases, type = "scatter", mode = "lines") %>% add_trace(x = ~date, y = ~new_deaths, type = "scatter", mode = "lines") 

There is around a month delay between peaks of cases and peaks of deaths.

Step 9: Heatmaps

cv_states_mat <- cv_states %>% select(state, date, new_cases) %>% dplyr::filter(date>as.Date("2021-06-15"))
cv_states_mat2 <- as.data.frame(pivot_wider(cv_states_mat, names_from = state, values_from = new_cases))
rownames(cv_states_mat2) <- cv_states_mat2$date
cv_states_mat2$date <- NULL
cv_states_mat2 <- as.matrix(cv_states_mat2)
# Create a heatmap using plot_ly()
plot_ly(x=colnames(cv_states_mat2), y=rownames(cv_states_mat2),
             z=~cv_states_mat2,
             type="heatmap",
             showscale=T)

The states that stand out are California, New york, and Texas.

# Repeat with newper100k
cv_states_mat <- cv_states %>% select(state, date, newper100k) %>% dplyr::filter(date>as.Date("2021-06-15"))
cv_states_mat2 <- as.data.frame(pivot_wider(cv_states_mat, names_from = state, values_from = newper100k))
rownames(cv_states_mat2) <- cv_states_mat2$date
cv_states_mat2$date <- NULL
cv_states_mat2 <- as.matrix(cv_states_mat2)
plot_ly(x=colnames(cv_states_mat2), y=rownames(cv_states_mat2),
             z=~cv_states_mat2,
             type="heatmap",
             showscale=T)

The states that now stand out are Rhode Island, New York, New Jersey, and Alaska.

# Create a second heatmap after filtering to only include dates every other week
filter_dates <- seq(as.Date("2021-06-15"), as.Date("2021-11-01"), by=14)
cv_states_mat <- cv_states %>% select(state, date, newper100k) %>% filter(date %in% filter_dates)
cv_states_mat2 <- as.data.frame(pivot_wider(cv_states_mat, names_from = state, values_from = newper100k))
rownames(cv_states_mat2) <- cv_states_mat2$date
cv_states_mat2$date <- NULL
cv_states_mat2 <- as.matrix(cv_states_mat2)
# Create a heatmap using plot_ly()
plot_ly(x=colnames(cv_states_mat2), y=rownames(cv_states_mat2),
             z=~cv_states_mat2,
             type="heatmap",
             showscale=T)

Step 10: Map

### For specified date

pick.date = "2021-10-15"

# Extract the data for each state by its abbreviation
cv_per100 <- cv_states %>% filter(date==pick.date) %>% select(state, abb, newper100k, cases, deaths) # select data
cv_per100$state_name <- cv_per100$state
cv_per100$state <- cv_per100$abb
cv_per100$abb <- NULL

# Create hover text
cv_per100$hover <- with(cv_per100, paste(state_name, '<br>', "Cases per 100k: ", newper100k, '<br>', "Cases: ", cases, '<br>', "Deaths: ", deaths))

# Set up mapping details
set_map_details <- list(
  scope = 'usa',
  projection = list(type = 'albers usa'),
  showlakes = TRUE,
  lakecolor = toRGB('white')
)

# Make sure both maps are on the same color scale
shadeLimit <- 125

# Create the map
fig <- plot_geo(cv_per100, locationmode = 'USA-states') %>% 
  add_trace(
    z = ~newper100k, text = ~hover, locations = ~state,
    color = ~newper100k, colors = 'Purples'
  )
fig <- fig %>% colorbar(title = paste0("Cases per 100k: ", pick.date), limits = c(0,shadeLimit))
fig <- fig %>% layout(
    title = paste('Cases per 100k by State as of ', pick.date, '<br>(Hover for value)'),
    geo = set_map_details
  )
fig_pick.date <- fig

#############
### Map for today's date

# Extract the data for each state by its abbreviation
cv_per100 <- cv_states_today %>%  select(state, abb, newper100k, cases, deaths) # select data
cv_per100$state_name <- cv_per100$state
cv_per100$state <- cv_per100$abb
cv_per100$abb <- NULL

# Create hover text
cv_per100$hover <- with(cv_per100, paste(state_name, '<br>', "Cases per 100k: ", newper100k, '<br>', "Cases: ", cases, '<br>', "Deaths: ", deaths))

# Set up mapping details
set_map_details <- list(
  scope = 'usa',
  projection = list(type = 'albers usa'),
  showlakes = TRUE,
  lakecolor = toRGB('white')
)

# Create the map
fig <- plot_geo(cv_per100, locationmode = 'USA-states') %>% 
  add_trace(
    z = ~newper100k, text = ~hover, locations = ~state,
    color = ~newper100k, colors = 'Purples'
  )
fig <- fig %>% colorbar(title = paste0("Cases per 100k: ", Sys.Date()), limits = c(0,shadeLimit))
fig <- fig %>% layout(
    title = paste('Cases per 100k by State as of', Sys.Date(), '<br>(Hover for value)'),
    geo = set_map_details
  )
fig_Today <- fig


### Plot together 
subplot(fig_pick.date, fig_Today, nrows = 2, margin = .05)

In 2021 there were a lot more states with many cases per 100k that were above 20 and even some that were close to 100. In 2023, most states have less than 10 cases of covid per 100k.